@echomem/mcp@1.4.39
EchoMem MCP bridge: cloud-first memory tools and the Agent Doctor workspace forensics report (cost ledger + 3D repo city)
AI Security Review
scanned 3mo ago · by lpm-firewall-aiNo concrete malware, unconsented install hook, credential theft, or covert exfiltration was found. Warn because explicit setup mutates broad AI-agent control surfaces and the server can auto-install future code.
Decision evidence
public snapshot- dist/setup.js: init/setup writes MCP entries and global agent guidance.
- dist/hud/hooks.js: explicit setup can register Codex/Claude command hooks.
- dist/headless-runtime.js: background update installs and imports newer package runtime.
- package.json has no preinstall/install/postinstall lifecycle hooks.
- Mutations are reached through explicit init/setup or HUD commands, not npm installation.
- Network use targets EchoMem APIs and npm registry; no credential-harvesting or covert exfiltration found.
- Child-process calls use fixed executables/arguments for CLI integration.
Source & flagged code
6 flaggedPackage source references dynamic require/import behavior.
dist/headless-runtime.jsView on unpkg · L65Findings
Affected versions and remediation
This report applies to @echomem/mcp@1.4.39.
See all versions of @echomem/mcp for other recorded verdicts.
- Review the evidence and your use of @echomem/mcp@1.4.39 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.